Multistage Real-Time Fire Detection Using Convolutional Neural Networks and Long Short-Term Memory Networks
Fire is one of the most commonly occurring disasters and is the main cause of catastrophic personal injury and devastating property damage. An early detection system is necessary to prevent fires from spreading out of control. In this paper, we propose a multistage fire detection method using convol...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2021-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9584840/ |
| _version_ | 1818743375446147072 |
|---|---|
| author | Manh Dung Nguyen Hoai Nam Vu Duc Cuong Pham Bokgil Choi Soonghwan Ro |
| author_facet | Manh Dung Nguyen Hoai Nam Vu Duc Cuong Pham Bokgil Choi Soonghwan Ro |
| author_sort | Manh Dung Nguyen |
| collection | DOAJ |
| description | Fire is one of the most commonly occurring disasters and is the main cause of catastrophic personal injury and devastating property damage. An early detection system is necessary to prevent fires from spreading out of control. In this paper, we propose a multistage fire detection method using convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. In the first stage, fire candidates are detected by using their salient features, such as their color, flickering frequency, and brightness. In the second stage, a pretrained CNN model is used to extract the 2D features of flames that are the input for the LSTM network. In the last stage, a softmax classifier is utilized to determine whether the flames represent a true fire or a nonfire moving object. The experimental results show that our proposed method can achieve competitive performance compared with other state-of-the-art methods and is suitable for real-world applications. |
| first_indexed | 2024-12-18T02:27:25Z |
| format | Article |
| id | doaj.art-acf21ac3520745d5bfa8161573b7ecbe |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-18T02:27:25Z |
| publishDate | 2021-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-acf21ac3520745d5bfa8161573b7ecbe2022-12-21T21:24:00ZengIEEEIEEE Access2169-35362021-01-01914666714667910.1109/ACCESS.2021.31223469584840Multistage Real-Time Fire Detection Using Convolutional Neural Networks and Long Short-Term Memory NetworksManh Dung Nguyen0https://orcid.org/0000-0001-6165-4137Hoai Nam Vu1https://orcid.org/0000-0001-5290-2258Duc Cuong Pham2https://orcid.org/0000-0003-2793-6821Bokgil Choi3Soonghwan Ro4https://orcid.org/0000-0001-6091-796XDepartment of Electronic Engineering, Posts and Telecommunications Institute of Technology, Hanoi, VietnamDepartment of Computer Science, Posts and Telecommunications Institute of Technology, Hanoi, VietnamIVS Vietnam Company, Hanoi, VietnamDepartment of Electrical Engineering, Kongju National University, Cheonan, South KoreaDepartment of Information and Communication, Kongju National University, Cheonan, South KoreaFire is one of the most commonly occurring disasters and is the main cause of catastrophic personal injury and devastating property damage. An early detection system is necessary to prevent fires from spreading out of control. In this paper, we propose a multistage fire detection method using convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. In the first stage, fire candidates are detected by using their salient features, such as their color, flickering frequency, and brightness. In the second stage, a pretrained CNN model is used to extract the 2D features of flames that are the input for the LSTM network. In the last stage, a softmax classifier is utilized to determine whether the flames represent a true fire or a nonfire moving object. The experimental results show that our proposed method can achieve competitive performance compared with other state-of-the-art methods and is suitable for real-world applications.https://ieeexplore.ieee.org/document/9584840/Fire detectionconvolutional neural networkImageNetlong short-term memory |
| spellingShingle | Manh Dung Nguyen Hoai Nam Vu Duc Cuong Pham Bokgil Choi Soonghwan Ro Multistage Real-Time Fire Detection Using Convolutional Neural Networks and Long Short-Term Memory Networks IEEE Access Fire detection convolutional neural network ImageNet long short-term memory |
| title | Multistage Real-Time Fire Detection Using Convolutional Neural Networks and Long Short-Term Memory Networks |
| title_full | Multistage Real-Time Fire Detection Using Convolutional Neural Networks and Long Short-Term Memory Networks |
| title_fullStr | Multistage Real-Time Fire Detection Using Convolutional Neural Networks and Long Short-Term Memory Networks |
| title_full_unstemmed | Multistage Real-Time Fire Detection Using Convolutional Neural Networks and Long Short-Term Memory Networks |
| title_short | Multistage Real-Time Fire Detection Using Convolutional Neural Networks and Long Short-Term Memory Networks |
| title_sort | multistage real time fire detection using convolutional neural networks and long short term memory networks |
| topic | Fire detection convolutional neural network ImageNet long short-term memory |
| url | https://ieeexplore.ieee.org/document/9584840/ |
| work_keys_str_mv | AT manhdungnguyen multistagerealtimefiredetectionusingconvolutionalneuralnetworksandlongshorttermmemorynetworks AT hoainamvu multistagerealtimefiredetectionusingconvolutionalneuralnetworksandlongshorttermmemorynetworks AT duccuongpham multistagerealtimefiredetectionusingconvolutionalneuralnetworksandlongshorttermmemorynetworks AT bokgilchoi multistagerealtimefiredetectionusingconvolutionalneuralnetworksandlongshorttermmemorynetworks AT soonghwanro multistagerealtimefiredetectionusingconvolutionalneuralnetworksandlongshorttermmemorynetworks |